A multi-agent intelligent system for detecting unknown adverse drug reactions through communication and collaboration

A MULTI-AGENT INTELLIGENT SYSTEM FOR DETECTING UNKNOWNADVERSE DRUG REACTIONS THROUGH COMMUNICATION ANDCOLLABORATIONby AYMAN MANSOURDecember 2012 Advisor: Prof. Hao YingMajor: Electrical EngineeringDegree: Doctor of PhilosophySeveral thousands of drugs are currently available on the U.S. market. A completeunderstanding of the safe use of drugs is not possible at the time when drug is developed ormarketed. At that time, the safety information is only obtained from a few thousand peoplein a typical pre-marketing clinical trial. Clinical trials are not capable of detecting rareadverse drug reactions (ADRs) because of limitations in sample size and trial duration.Early detection of unknown ADRs could save lives and prevent unnecessaryhospitalizations. Current methods largely rely on spontaneous reports which suffer fromserious underreporting, latency, and inconsistent reporting. Thus they are not ideal forrapidly identifying rare ADRs. In this dissertation, I developed a team-based multi-agentintelligent system approach for proactively detecting potential ADR signal pairs (i.e.,potential links between drugs and apparent adverse reactions). The basic idea is thatintelligent agents are capable of collaborating with one another by sharing information and